CNN-LSTM optimized with SWATS for accurate state-of-charge estimation in lithium-ion batteries considering internal resistance

Abstract Accurately estimating the state-of-charge (SOC) of lithium-ion batteries is of great significance for the energy management and range calculation of electric vehicles. With the development of graphics processing units, SOC estimation based on data-driven methods, especially using recurrent...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhaowei Zhang, Chen Liu, Tianyu Li, Tian Wang, Yaoyao Cui, Pengcheng Zhao
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-15597-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849332983032446976
author Zhaowei Zhang
Chen Liu
Tianyu Li
Tian Wang
Yaoyao Cui
Pengcheng Zhao
author_facet Zhaowei Zhang
Chen Liu
Tianyu Li
Tian Wang
Yaoyao Cui
Pengcheng Zhao
author_sort Zhaowei Zhang
collection DOAJ
description Abstract Accurately estimating the state-of-charge (SOC) of lithium-ion batteries is of great significance for the energy management and range calculation of electric vehicles. With the development of graphics processing units, SOC estimation based on data-driven methods, especially using recurrent neural networks, has received considerable attention in recent years. However, existing data-driven methods often neglect internal resistance, which is highly detrimental to the accuracy of SOC estimation. In addition, commonly used network optimization algorithms do not always maximize the convergence speed and performance simultaneously. To solve these problems, this paper describes a battery test bench for producing an effective lithium-ion battery dataset containing current, voltage, temperature, and more importantly, internal resistance measurements. To improve the estimated SOC performance, the internal resistance is considered in the construction of a data-driven model. Using a convolutional neural network (CNN) and long short-term memory (LSTM), we propose an optimization model that switches from Adam to stochastic gradient descent (SWATS). A well-known public battery dataset and an experimentally measured dataset are used to verify the feasibility of the SWATS scheme. The results show that, compared with existing data-driven methods, the proposed method is effective, especially in terms of robustness and generalization.
format Article
id doaj-art-971176ee3ef34cfda5937e1c0cc1637a
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-971176ee3ef34cfda5937e1c0cc1637a2025-08-20T03:46:01ZengNature PortfolioScientific Reports2045-23222025-08-0115111610.1038/s41598-025-15597-2CNN-LSTM optimized with SWATS for accurate state-of-charge estimation in lithium-ion batteries considering internal resistanceZhaowei Zhang0Chen Liu1Tianyu Li2Tian Wang3Yaoyao Cui4Pengcheng Zhao5School of Mechanical and Electrical Engineering, Shijiazhuang UniversitySchool of Mechanical and Electrical Engineering, CSPC Zhongnuo Pharmaceutical (Shijiazhuang) Co., Ltd.,School of Mechanical and Electrical Engineering, Wooking Scientific Instrument Co., Ltd.,School of Mechanical and Electrical Engineering, Shijiazhuang UniversitySchool of Mechanical and Electrical Engineering, Shijiazhuang UniversitySchool of Mechanical and Electrical Engineering, Shijiazhuang UniversityAbstract Accurately estimating the state-of-charge (SOC) of lithium-ion batteries is of great significance for the energy management and range calculation of electric vehicles. With the development of graphics processing units, SOC estimation based on data-driven methods, especially using recurrent neural networks, has received considerable attention in recent years. However, existing data-driven methods often neglect internal resistance, which is highly detrimental to the accuracy of SOC estimation. In addition, commonly used network optimization algorithms do not always maximize the convergence speed and performance simultaneously. To solve these problems, this paper describes a battery test bench for producing an effective lithium-ion battery dataset containing current, voltage, temperature, and more importantly, internal resistance measurements. To improve the estimated SOC performance, the internal resistance is considered in the construction of a data-driven model. Using a convolutional neural network (CNN) and long short-term memory (LSTM), we propose an optimization model that switches from Adam to stochastic gradient descent (SWATS). A well-known public battery dataset and an experimentally measured dataset are used to verify the feasibility of the SWATS scheme. The results show that, compared with existing data-driven methods, the proposed method is effective, especially in terms of robustness and generalization.https://doi.org/10.1038/s41598-025-15597-2State-of-chargeSwitchesInternal resistanceLithium-ion battery
spellingShingle Zhaowei Zhang
Chen Liu
Tianyu Li
Tian Wang
Yaoyao Cui
Pengcheng Zhao
CNN-LSTM optimized with SWATS for accurate state-of-charge estimation in lithium-ion batteries considering internal resistance
Scientific Reports
State-of-charge
Switches
Internal resistance
Lithium-ion battery
title CNN-LSTM optimized with SWATS for accurate state-of-charge estimation in lithium-ion batteries considering internal resistance
title_full CNN-LSTM optimized with SWATS for accurate state-of-charge estimation in lithium-ion batteries considering internal resistance
title_fullStr CNN-LSTM optimized with SWATS for accurate state-of-charge estimation in lithium-ion batteries considering internal resistance
title_full_unstemmed CNN-LSTM optimized with SWATS for accurate state-of-charge estimation in lithium-ion batteries considering internal resistance
title_short CNN-LSTM optimized with SWATS for accurate state-of-charge estimation in lithium-ion batteries considering internal resistance
title_sort cnn lstm optimized with swats for accurate state of charge estimation in lithium ion batteries considering internal resistance
topic State-of-charge
Switches
Internal resistance
Lithium-ion battery
url https://doi.org/10.1038/s41598-025-15597-2
work_keys_str_mv AT zhaoweizhang cnnlstmoptimizedwithswatsforaccuratestateofchargeestimationinlithiumionbatteriesconsideringinternalresistance
AT chenliu cnnlstmoptimizedwithswatsforaccuratestateofchargeestimationinlithiumionbatteriesconsideringinternalresistance
AT tianyuli cnnlstmoptimizedwithswatsforaccuratestateofchargeestimationinlithiumionbatteriesconsideringinternalresistance
AT tianwang cnnlstmoptimizedwithswatsforaccuratestateofchargeestimationinlithiumionbatteriesconsideringinternalresistance
AT yaoyaocui cnnlstmoptimizedwithswatsforaccuratestateofchargeestimationinlithiumionbatteriesconsideringinternalresistance
AT pengchengzhao cnnlstmoptimizedwithswatsforaccuratestateofchargeestimationinlithiumionbatteriesconsideringinternalresistance